A Nigerian Develops A Video-Based Vehicle Counting System, You Need To See This

Nigerians are a bundle of talents and so they excelled in their given career despite having little or nothing to work on.

Traffic congestion is a major challenge in many cities around the world, especially cities in developing nations where road networks are poorly designed and cities overpopulated. Collecting quality data about the flow of traffic is crucial in traffic management, as jams can be anticipated and prevented, and vehicles can be intelligently directed to routes with less traffic.

This project aims to improve the traffic situation on, and condition of Nigerian roads by implementing a vehicle counting system that provides accurate data for traffic control agencies and systems.

The significances of this system include estimating traffic flow on a given road per time, predicting future traffic conditions, understanding traffic patterns and the factors that affect them, and optimizing existing manual traffic management systems.

A final year student of the university has developed a video-based vehicle counting system. The model was built using OpenCV (Python) and a pre-trained YOLO v3 object detection model. With this model, it can help to count the number of cars that pass through a certain road in minutes. Imagine if we want to take the data analysis of the number of cars that pass through 3rd Mainland Bridge in 2 minutes, this counting system will be best used.

How it works
The vehicle counting system is made up of three main components: a detector, tracker and counter. The detector identifies vehicles in a given frame of video and returns a list of bounding boxes around the vehicles to the tracker. The tracker uses the bounding boxes to obtain regions of interest (ROIs) and uses them to track the vehicles in subsequent frames. The detector is also used to update tracker objects periodically to ensure that they are still tracking the vehicles correctly. The counter draws counting lines across the road. When a vehicle crosses the line, the vehicle count is incremented.
Many Nigerians have been pouring encomiums on him and many are already seeking partnerships already.

See below the video

1/2 I worked on a video-based vehicle counting system for my final year (BSc) project. It gave me the opportunity to finally dive into Computer Vision. It was built using OpenCV (Python) and a pre-trained YOLO v3 object detection model. Accuracy is not that bad IMO. pic.twitter.com/BpjR85DtcW

— Nicholas Kajoh (@nicholaskajoh) April 7, 2019

Credit:
Nicholas